Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sign up prompts and newsletter subscription instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to signing up for newsletters or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wolves
    -0.64
    abal
    -0.63
    kell
    -0.62
    mith
    -0.62
    tten
    -0.61
    rendered
    -0.60
     Haas
    -0.60
     hurd
    -0.59
    liest
    -0.58
    abouts
    -0.58
    POSITIVE LOGITS
     guiActive
    0.81
     unlocks
    0.78
     Password
    0.71
    irmation
    0.70
     Partnership
    0.69
     Username
    0.67
    again
    0.67
     TAMADRA
    0.66
     button
    0.65
    dayName
    0.64
    Act Density 0.030%

    No Known Activations